pith. sign in

arXiv preprint arXiv:2407.03876 , year=

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CR 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Adaptive Instruction Composition for Automated LLM Red-Teaming

cs.CR · 2026-04-22 · unverdicted · novelty 7.0

Adaptive Instruction Composition uses a neural contextual bandit with RL to adaptively combine crowdsourced texts, generating more effective and diverse LLM jailbreaks than random or prior adaptive methods on Harmbench.

citing papers explorer

Showing 1 of 1 citing paper.

  • Adaptive Instruction Composition for Automated LLM Red-Teaming cs.CR · 2026-04-22 · unverdicted · none · ref 47

    Adaptive Instruction Composition uses a neural contextual bandit with RL to adaptively combine crowdsourced texts, generating more effective and diverse LLM jailbreaks than random or prior adaptive methods on Harmbench.